Experience
Software Engineer II
Microsoft, Outlook Copilot 2022 – Present- Drove end-to-end development of an LLM-powered meeting preparation feature, from internal experimentation through global deployment, achieving 75%+ user satisfaction across millions of users
- Built a calendar management agent that uses an LLM to analyze calendar data and execute commands via natural language — creating, deleting, and editing meetings with 85% task completion on internal benchmarks
- Optimized skill orchestration and time expression understanding for a meeting time suggestion feature, resulting in a 5x increase in kept suggestions
- Devised a novel RL method based on Direct Nash Optimization, using single-example LoRA in place of contrastive learning and cutting required GPUs from hundreds to tens
- Built a distributed RL training pipeline with a local data emulator and custom reward functions, improving performance on an internal M365 tool-calling eval by 30% over the base model
- Engineered data pipelines with LLM-based verification and correction loops, producing 100K+ Outlook calendar entities powering 5+ features including Event Importance classification
Research Assistant
University of Michigan, Nallasamy Lab 2021 – 2022- Developed a surgical tool identification model with a lightweight CNN and post-process prediction averaging, achieving state-of-the-art performance with 30% fewer parameters
- Built a custom 3D DenseNet by stacking filter weights in the temporal dimension for spatio-temporal feature extraction, achieving state-of-the-art results on cataract surgery step identification
Publications
Nicholas Matton, et al. "Analysis of Cataract Surgery Instrument Identification Performance of Convolutional and Recurrent Neural Network Ensembles Leveraging BigCat"
Translational Vision Science and Technology, Volume 11, Issue 4, 2022
Ossama Mahmoud, Han Zhang, Nicholas Matton, et al. "CatStep: Automated Cataract Surgical Phase Classification and Boundary Segmentation Leveraging Inflated 3D-Convolutional Neural Network Architectures and BigCat"
Ophthalmology Science, Volume 4, Issue 1, 2024
Education
M.S. Computer Science and Engineering
University of Michigan, Ann Arbor 2017 – 20223.92/4.00 GPA
B.S. Computer Science and Engineering
University of Michigan, Ann Arbor 2017 – 20223.92/4.00 GPA, Minor in Mathematics, Summa Cum Laude
